EP4145353A4 - Verfahren und vorrichtung zur konstruktion eines neuronalen netzwerks - Google Patents

Verfahren und vorrichtung zur konstruktion eines neuronalen netzwerks Download PDF

Info

Publication number
EP4145353A4
EP4145353A4 EP21813687.7A EP21813687A EP4145353A4 EP 4145353 A4 EP4145353 A4 EP 4145353A4 EP 21813687 A EP21813687 A EP 21813687A EP 4145353 A4 EP4145353 A4 EP 4145353A4
Authority
EP
European Patent Office
Prior art keywords
constructing
neuronal network
neuronal
network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP21813687.7A
Other languages
English (en)
French (fr)
Other versions
EP4145353A1 (de
Inventor
Chenhan JIANG
Hang Xu
Zhenguo Li
Xiaodan Liang
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of EP4145353A1 publication Critical patent/EP4145353A1/de
Publication of EP4145353A4 publication Critical patent/EP4145353A4/de
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/096—Transfer learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/94—Hardware or software architectures specially adapted for image or video understanding
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/96—Management of image or video recognition tasks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Neurology (AREA)
  • Image Analysis (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
EP21813687.7A 2020-05-25 2021-03-23 Verfahren und vorrichtung zur konstruktion eines neuronalen netzwerks Pending EP4145353A4 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010448652.7A CN111797983B (zh) 2020-05-25 2020-05-25 一种神经网络构建方法以及装置
PCT/CN2021/082222 WO2021238366A1 (zh) 2020-05-25 2021-03-23 一种神经网络构建方法以及装置

Publications (2)

Publication Number Publication Date
EP4145353A1 EP4145353A1 (de) 2023-03-08
EP4145353A4 true EP4145353A4 (de) 2023-10-25

Family

ID=72806177

Family Applications (1)

Application Number Title Priority Date Filing Date
EP21813687.7A Pending EP4145353A4 (de) 2020-05-25 2021-03-23 Verfahren und vorrichtung zur konstruktion eines neuronalen netzwerks

Country Status (4)

Country Link
US (1) US20230089380A1 (de)
EP (1) EP4145353A4 (de)
CN (1) CN111797983B (de)
WO (1) WO2021238366A1 (de)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10635813B2 (en) 2017-10-06 2020-04-28 Sophos Limited Methods and apparatus for using machine learning on multiple file fragments to identify malware
US11003774B2 (en) 2018-01-26 2021-05-11 Sophos Limited Methods and apparatus for detection of malicious documents using machine learning
US11941491B2 (en) 2018-01-31 2024-03-26 Sophos Limited Methods and apparatus for identifying an impact of a portion of a file on machine learning classification of malicious content
WO2020030913A1 (en) 2018-08-07 2020-02-13 Sophos Limited Methods and apparatus for management of a machine-learning model to adapt to changes in landscape of potentially malicious artifacts
US11947668B2 (en) 2018-10-12 2024-04-02 Sophos Limited Methods and apparatus for preserving information between layers within a neural network
CN111797983B (zh) * 2020-05-25 2024-12-03 华为技术有限公司 一种神经网络构建方法以及装置
CN112633471B (zh) * 2020-12-17 2023-09-26 苏州浪潮智能科技有限公司 构建神经网络架构搜索框架的方法、系统、设备及介质
CN112686371A (zh) * 2020-12-25 2021-04-20 深圳前海微众银行股份有限公司 网络结构搜索方法、装置、设备、存储介质及程序产品
CN114692861B (zh) * 2020-12-28 2026-01-16 华为技术有限公司 计算图更新方法、计算图处理方法以及相关设备
CN113031437B (zh) * 2021-02-26 2022-10-25 同济大学 一种基于动态模型强化学习的倒水服务机器人控制方法
US12010129B2 (en) * 2021-04-23 2024-06-11 Sophos Limited Methods and apparatus for using machine learning to classify malicious infrastructure
CN112990448B (zh) * 2021-04-26 2021-08-03 清华大学 用于计算的方法、计算系统、计算设备和介质
CN115345305A (zh) * 2021-05-12 2022-11-15 华为云计算技术有限公司 一种推理系统、方法、装置及相关设备
CN113920514B (zh) * 2021-06-18 2024-11-12 上海悠络客电子科技股份有限公司 一种面向目标检测的高效进化神经网络架构搜索方法
CN113743606B (zh) * 2021-09-08 2024-12-17 广州文远知行科技有限公司 一种神经网络的搜索方法、装置、计算机设备和存储介质
CN113792876B (zh) 2021-09-16 2023-08-29 北京百度网讯科技有限公司 骨干网络的生成方法、装置、设备以及存储介质
CN113988272B (zh) * 2021-11-08 2025-11-18 上海商汤智能科技有限公司 一种生成神经网络的方法、装置、计算机设备和存储介质
CN114492765B (zh) * 2022-02-24 2024-09-13 腾讯科技（深圳）有限公司 一种模型优化方法、装置、设备及存储介质、程序产品
CN114995782B (zh) * 2022-08-03 2022-10-25 上海登临科技有限公司 数据处理方法、装置、设备和可读存储介质
CN116205905B (zh) * 2023-04-25 2023-07-21 合肥中科融道智能科技有限公司 基于移动端的配电网施工安全及质量图像检测方法及系统
CN117234095B (zh) * 2023-08-18 2024-04-02 浙江雨林电子科技有限公司 一种全屋家居无线智能控制方法及系统
CN117010447B (zh) * 2023-10-07 2024-01-23 成都理工大学 基于端到端的可微架构搜索方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200143231A1 (en) * 2018-11-02 2020-05-07 Microsoft Technology Licensing, Llc Probabilistic neural network architecture generation

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1889560A (zh) * 2005-08-03 2007-01-03 华为技术有限公司 网际协议多媒体子系统中面向用户的网络拓扑隐藏方法
US10346727B2 (en) * 2016-10-28 2019-07-09 Adobe Inc. Utilizing a digital canvas to conduct a spatial-semantic search for digital visual media
CN108229647A (zh) * 2017-08-18 2018-06-29 北京市商汤科技开发有限公司 神经网络结构的生成方法和装置、电子设备、存储介质
WO2019108923A1 (en) * 2017-11-30 2019-06-06 Google Llc Neural architecture search using a performance prediction neural network
US11164079B2 (en) * 2017-12-15 2021-11-02 International Business Machines Corporation Multi-GPU deep learning using CPUs
CN108917583B (zh) * 2018-05-18 2019-04-23 长安大学 一种顾及对流层延迟影响的超高层建筑形变监测新方法
CN109284820A (zh) * 2018-10-26 2019-01-29 北京图森未来科技有限公司 一种深度神经网络的结构搜索方法及装置
CN120509449A (zh) * 2019-01-23 2025-08-19 谷歌有限责任公司 用于神经网络的复合模型缩放
CN110175671B (zh) * 2019-04-28 2022-12-27 华为技术有限公司 神经网络的构建方法、图像处理方法及装置
CN110097176A (zh) * 2019-05-07 2019-08-06 东华理工大学 一种应用于空气质量大数据异常检测的神经网络结构搜索方法
CN110334802B (zh) * 2019-05-23 2025-02-18 腾讯科技（深圳）有限公司 一种神经网络模型的构建方法、装置、设备及存储介质
CN110363810B (zh) * 2019-06-14 2021-07-16 北京百度网讯科技有限公司 建立图像检测模型的方法、装置、设备和计算机存储介质
CN111126564B (zh) * 2019-11-27 2023-08-08 东软集团股份有限公司 一种神经网络结构搜索方法、装置及设备
US11475313B2 (en) * 2020-02-13 2022-10-18 International Business Machines Corporation Unsupervised, semi-supervised, and supervised learning using deep learning based probabilistic generative models
US11665180B2 (en) * 2020-02-28 2023-05-30 International Business Machines Corporation Artificially intelligent security incident and event management
CN111797983B (zh) * 2020-05-25 2024-12-03 华为技术有限公司 一种神经网络构建方法以及装置

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200143231A1 (en) * 2018-11-02 2020-05-07 Microsoft Technology Licensing, Llc Probabilistic neural network architecture generation

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
See also references of WO2021238366A1 *
WEI WEN ET AL: "AutoGrow: Automatic Layer Growing in Deep Convolutional Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 7 June 2019 (2019-06-07), XP081374300 *

Also Published As

Publication number Publication date
CN111797983B (zh) 2024-12-03
EP4145353A1 (de) 2023-03-08
US20230089380A1 (en) 2023-03-23
CN111797983A (zh) 2020-10-20
WO2021238366A1 (zh) 2021-12-02

Similar Documents

Publication Publication Date Title
EP4145353A4 (de) Verfahren und vorrichtung zur konstruktion eines neuronalen netzwerks
EP4145351A4 (de) Verfahren und system zur konstruktion eines neuronalen netzes
EP4163831A4 (de) Verfahren und vorrichtung zur destillation eines neuronalen netzwerks
EP4131077A4 (de) Verfahren und vorrichtung zur optimierung eines neuronalen netzwerks
EP3633557A4 (de) Vorrichtung und verfahren zur berechnung eines neuronalen netzes
EP4191428A4 (de) Verfahren und vorrichtung zur konstruktion eines wissensgraphen
EP3949517C0 (de) Verfahren und vorrichtung zur durchführung eines übergabeverfahrens
EP3674728A4 (de) Verfahren und vorrichtung zur schätzung eines soc-ocv-profils
EP4316935A4 (de) Verfahren und vorrichtung zur gewinnung eines spurwechselbereichs
EP4191221A4 (de) Verfahren und vorrichtung zur konstruktion eines fahrzeugsimulationstestszenarios
EP4339843A4 (de) Verfahren und vorrichtung zur optimierung eines neuronalen netzwerks
EP4226257A4 (de) Verfahren und vorrichtung für eine verteilte datenbank in einem netzwerk
EP4394656A4 (de) Verfahren zur optimierung eines neuronalen netzwerkmodells und zugehörige vorrichtung
EP4160399A4 (de) Verfahren und vorrichtung zur ausführung eines prozesses
EP4155114A4 (de) Vorrichtung zur erstellung eines reiseplans und verfahren zur erstellung eines reiseplans
EP4300899A4 (de) Vorrichtung und verfahren zur konstruktion eines virtuellen unternehmensnetzwerks
EP4093140A4 (de) Verfahren und vorrichtung zur auswahl eines direktzugriffstyps
EP4433935A4 (de) Vorrichtung und verfahren zur simulation eines dreidimensionalen objekts
EP4206978A4 (de) Verfahren und vorrichtung zur identifizierung eines zielobjekts
EP4153919C0 (de) Verfahren und vorrichtung zum konfigurieren eines belüftungssystems
EP4214025A4 (de) Verfahren und vorrichtung zur verwaltung eines roboterweges
EP4492754A4 (de) Verfahren und vorrichtung zur planung eines inhaltsbereitstellungsnetzwerkdomänennamens
EP4270236C0 (de) Verfahren und vorrichtung zur bereitstellung eines empfehlungssystems
DE112021001244A5 (de) Verfahren und Vorrichtung zur Durchführung eines qPCR-Verfahrens
EP4082717C0 (de) Verarbeitungsblock und verfahren zur positionierung eines verarbeitungsblocks

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20221128

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Free format text: PREVIOUS MAIN CLASS: G06N0003063000

Ipc: G06N0003045000

A4 Supplementary search report drawn up and despatched

Effective date: 20230925

RIC1 Information provided on ipc code assigned before grant

Ipc: G06V 10/44 20220101ALI20230919BHEP

Ipc: G06V 10/96 20220101ALI20230919BHEP

Ipc: G06V 10/94 20220101ALI20230919BHEP

Ipc: G06V 10/82 20220101ALI20230919BHEP

Ipc: G06N 3/096 20230101ALI20230919BHEP

Ipc: G06N 3/082 20230101ALI20230919BHEP

Ipc: G06N 3/0464 20230101ALI20230919BHEP

Ipc: G06N 3/045 20230101AFI20230919BHEP